{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/one-pixel-attack-for-fooling-deep-neural","title":"One pixel attack for fooling deep neural networks","arxiv_id":"1710.08864","date":"2017-10-24","proceeding":null,"authors":["Jiawei Su","Danilo Vasconcellos Vargas","Sakurai Kouichi"],"abstract":"Recent research has revealed that the output of Deep Neural Networks (DNN) can be easily altered by adding relatively small perturbations to the input vector. In this paper, we analyze an attack in an extremely limited scenario where only one pixel can be modified. For that we propose a novel method for generating one-pixel adversarial perturbations based on differential evolution (DE). It requires less adversarial information (a black-box attack) and can fool more types of networks due to the inherent features of DE. The results show that 67.97% of the natural images in Kaggle CIFAR-10 test dataset and 16.04% of the ImageNet (ILSVRC 2012) test images can be perturbed to at least one target class by modifying just one pixel with 74.03% and 22.91% confidence on average. We also show the same vulnerability on the original CIFAR-10 dataset. Thus, the proposed attack explores a different take on adversarial machine learning in an extreme limited scenario, showing that current DNNs are also vulnerable to such low dimension attacks. Besides, we also illustrate an important application of DE (or broadly speaking, evolutionary computation) in the domain of adversarial machine learning: creating tools that can effectively generate low-cost adversarial attacks against neural networks for evaluating robustness.","url_abs":"https://arxiv.org/abs/1710.08864v7","url_pdf":"https://arxiv.org/pdf/1710.08864v7.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"one-pixel-attack-for-fooling-deep-neural","repo_url":"https://github.com/DebangLi/one-pixel-attack-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"one-pixel-attack-for-fooling-deep-neural","repo_url":"https://github.com/Gapeh/onePixelAttack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"one-pixel-attack-for-fooling-deep-neural","repo_url":"https://github.com/Hyperparticle/one-pixel-attack-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"one-pixel-attack-for-fooling-deep-neural","repo_url":"https://github.com/YuanGongND/realtime-adversarial-attack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"one-pixel-attack-for-fooling-deep-neural","repo_url":"https://github.com/chihchenghsieh/eventlogdice","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"one-pixel-attack-for-fooling-deep-neural","repo_url":"https://github.com/jeaneudesAyilo/new-hands-on-2021","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"one-pixel-attack-for-fooling-deep-neural","repo_url":"https://github.com/timroith/adversarialcbo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.08864","atlas_url":"https://app.syntology.ai/?focus=1710.08864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.08864"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/timroith/adversarialcbo","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Gapeh/onePixelAttack","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DebangLi/one-pixel-attack-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YuanGongND/realtime-adversarial-attack","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chihchenghsieh/eventlogdice","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Hyperparticle/one-pixel-attack-keras","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jeaneudesAyilo/new-hands-on-2021","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"00387757fde35849","entry":"attack_stats","repo":"Hyperparticle/one-pixel-attack-keras","repo_kind":"listed","path":"helper.py","file_url":"https://github.com/Hyperparticle/one-pixel-attack-keras/blob/HEAD/helper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00387757fde35849"}},{"code_sha256_prefix":"3c76b056d09eb491","entry":"evaluate_models","repo":"Hyperparticle/one-pixel-attack-keras","repo_kind":"listed","path":"helper.py","file_url":"https://github.com/Hyperparticle/one-pixel-attack-keras/blob/HEAD/helper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c76b056d09eb491"}},{"code_sha256_prefix":"944ce592f53c3744","entry":"fig_to_uri","repo":"jeaneudesAyilo/new-hands-on-2021","repo_kind":"listed","path":"app/apps/app_detection.py","file_url":"https://github.com/jeaneudesAyilo/new-hands-on-2021/blob/HEAD/app/apps/app_detection.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"944ce592f53c3744"}},{"code_sha256_prefix":"24c02b6f46231b2a","entry":"load_space","repo":"timroith/adversarialcbo","repo_kind":"listed","path":"advcbx/attackspace/load_attack.py","file_url":"https://github.com/timroith/adversarialcbo/blob/HEAD/advcbx/attackspace/load_attack.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"24c02b6f46231b2a"}},{"code_sha256_prefix":"26b08adf74ae76c9","entry":"pertub_image","repo":"jeaneudesAyilo/new-hands-on-2021","repo_kind":"listed","path":"app/apps/app_recognition.py","file_url":"https://github.com/jeaneudesAyilo/new-hands-on-2021/blob/HEAD/app/apps/app_recognition.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26b08adf74ae76c9"}},{"code_sha256_prefix":"fe38dc1eccd1f02b","entry":"perturb_image","repo":"Hyperparticle/one-pixel-attack-keras","repo_kind":"listed","path":"helper.py","file_url":"https://github.com/Hyperparticle/one-pixel-attack-keras/blob/HEAD/helper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fe38dc1eccd1f02b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}